Allow hflush/sync to occur in parallel with new writes to the file
--
Key: HDFS-895
URL: https://issues.apache.org/jira/browse/HDFS-895
Project: Hadoop HDFS
Issue Type:
Hello all,
Unless I'm missing something, the synchronization in FSNameSystemMetrics
on the 0.20 does not appear correct. It locks on itself while pulling
various metrics from the FSNameSystem object. For example,
FSNameSystem.getBlocksTotal() delegates to BlocksMap.size() which
delegates to the
ReplicasMap remove has a bug in generation stamp comparison
---
Key: HDFS-897
URL: https://issues.apache.org/jira/browse/HDFS-897
Project: Hadoop HDFS
Issue Type: Bug
[
https://issues.apache.org/jira/browse/HDFS-520?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Hairong Kuang reopened HDFS-520:
I am reopening this. Block recovery leads to the truncation of data thus has
the risk of losing data.
Any idea of what is wrong in the process?
I'd build using ant:
ant -Dcompile.c++=true -Dlibhdfs=true compile-c++-libhdfs
Thanks,
Eli
Sequential generation of block ids
--
Key: HDFS-898
URL: https://issues.apache.org/jira/browse/HDFS-898
Project: Hadoop HDFS
Issue Type: Improvement
Components: name-node
Affects Versions:
Corrupt replicas are not tracked correctly through block report from DN
---
Key: HDFS-900
URL: https://issues.apache.org/jira/browse/HDFS-900
Project: Hadoop HDFS
Issue